![](http://storage.googleapis.com/journals-stmjournals-com-wp-media-to-gcp-offload/2022/10/vector.jpg)
Rahul Raj,
![](http://storage.googleapis.com/journals-stmjournals-com-wp-media-to-gcp-offload/2022/10/vector.jpg)
Srijani Mondal,
- Student Cambridge Institute of Technology, Bengaluru, Karnataka, North Campus, India
- Student Cambridge Institute of Technology, North Campus, Bengaluru, Karnataka, India
Abstract
An AI system for automated exam grading is proposed. It tackles inefficiencies in human evaluation. The system uses TrOCR for accurate handwritten text recognition and a GPT model trained on graded responses for evaluation. This approach offers efficiency and reduced bias, but challenges remain. Evaluating open-ended questions and ensuring explainability require further development. It starts by looking at how AI technologies, such as machine learning, deep learning, and natural language processing, have developed and how they are being used to automate different parts of exam evaluation, such as grading, providing feedback, and spotting plagiarism. Additionally, it looks at how AI-driven assessment systems might improve learning outcomes, lessen the strain on teachers, and give students tailored feedback. But the research also points to several difficulties, including resolving privacy and data security issues and guaranteeing impartiality, accountability, and openness in AI-based assessments. Careful training and data curation are necessary to mitigate bias. The paper concludes by highlighting the need for the system to handle various question formats, address ambiguities, and integrate human review. This research presents a promising step towards a future of efficient, fair, and AI-powered exam grading.
Keywords: Autograding, TrOCR, GPT, Explainability, Debias
[This article belongs to Trends in Opto-electro & Optical Communication(toeoc)]
Browse Figures
References
- Cole, J. (2019). The time and resource implications of large-scale assessment. Assessment in Education: Principles, Policy & Practice, 26(5), 473-487. [doi: 10.1080/0953813X.2018.1508222]
- Ferguson, H. J., Gottschalk, R., & Roe, B. (2017). Race and gender bias in student discipline. Educational Researcher, 46(3), 130-141. [doi: 10.3102/0013189X17701242]
- Gupta, A., Iqbal, U., & Malik, M. A. (2023, January). TrOCR: A Reliable Transformer-Based Optical Character Recognition for Handwritten Text. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing (EMNLP) (pp. 1234-1245). Association for Computational Linguistics.
- Shi, B., Wang, X., Wang, H., Zhang, Z., & Luo, W. (2020). Deep learning for handwritten text recognition: A review. Journal of Graphics, Imaging and Vision, 4(2), 178-194. [doi: 10.1007/s11760-020-00203-8]
- Zhang, Y., Zhao, S., & Li, H. (2022, June). A Survey on Automated Essay Scoring with Deep Learning. arXiv preprint arXiv:2206.07223.
- Weller, S., Rozovskaya, A., & Mayfield, J. (2020). A multi-perspective evaluation of automated essay scoring systems. Journal of Artificial Intelligence in Education, 31(2), 229-252. [doi: 10.1007/s40563-020-00180-7]
- Singh B, Kapoor J, Nagpure SM, Kolhatkar SS, Chanore PG, Vishwakarma MM, Kokate RB. An Analysis of Automated Answer Evaluation Systems based on Machine Learning. In: Proceedings of the 3rd International Conference on Intelligent Computing and Control Systems, Madurai, India. 2019;696-702.
- Sultan MA, Salazar C, Sumner T, Fast and Easy Short Answer Grading with High Accuracy. In: Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing, Association for Computational Linguistics, Austin, Texas. 2016;1565-1570
- Rahman MA, Mahmud H. Automated Evaluation of Handwritten Answer Script Using Deep Learning Approach. In: Proceedings of the International Conference on Data Science and Information Technology, ACM, New York, NY. 2020;109-115.
- Chen, C.-Y., Liou, H.-C., Chang, J.S. (2006). Fast–and automatic generation system for grammar tests. In Proceedings of the COLING/ACL on Interactive Presentation Sessions. Association for Computational Linguistics, Sydney, (pp. 1–4).
![](http://storage.googleapis.com/journals-stmjournals-com-wp-media-to-gcp-offload/2022/10/25-150x150.jpg)
Trends in Opto-electro & Optical Communication
Volume | 14 |
Issue | 01 |
Received | April 23, 2024 |
Accepted | May 31, 2024 |
Published | August 8, 2024 |